Index Ai Academy
Foundation · Shapes, angles and waves

Angles, degrees and radians

Measuring a turn, converting units, arcs, and the angle between two arrows.

About 36 minutes · Free lesson

What it covers6

Why it matters

An angle measures a turn. People count turns in degrees, 360 to a full circle, but math and code count them in radians, where a full turn is 2π, about 6.28. Mixing the two up is one of the most common bugs in any program that draws, rotates or measures, because the code still runs and gives a wrong answer. In machine learning, the angle between two lists of numbers is how a model tells whether they point the same way, which is the idea behind comparing the meanings of words. This lesson sets up both units, the conversions between them, and the arc a turn sweeps out, so the next two lessons, on sine, cosine and waves, can use radians without a second thought.

What you'll be able to do

  • Measure a turn in degrees and in radians, and convert between them
  • Read a radian as the angle whose arc is one radius long, and find an arc's length
  • Use math.pi, math.radians and math.degrees, and avoid passing degrees where radians are expected
  • Read the angle between two arrows as how far apart their directions are, as ML does
Quick check
Have a guess before you start. How many degrees are in a quarter turn?
  1. 45
  2. 180
  3. 25
  4. 90
Show the answer

90

A full turn is 360°, so a quarter turn is 360 ÷ 4 = 90°: a right angle, like the corner of a page.

The math: measuring a turn

Purpose. Put a number on how far something has turned.

An angle is an amount of turning between two directions. The everyday unit is the degree: a full turn is 360°, a half turn 180°, a quarter turn (a right angle) 90°.

Math uses a second unit, the radian, built from the circle itself. Take a circle of any size and walk along its edge a distance equal to its radius. The angle you've turned through is 1 radian, about 57.3°. A full turn is the whole edge, 2π radii long, so a full turn is 2π radians:

360∘=2π radians180∘=π radians360^\circ = 2\pi \text{ radians} \qquad 180^\circ = \pi \text{ radians}

In plain words: half a turn is π radians, about 3.14. Everything else scales from that.

Quick check
From an earlier lesson: what is 120 as a fraction of 360, in simplest form?
  1. 12/36
  2. 1/3
  3. 3
  4. 1/4
Show the answer

1/3

120/360 simplifies by 120 to 1/3. So 120° is a third of a turn, and a third of 2π radians.

Converting through fractions of a turn. The easiest way to convert is to ask what fraction of a full turn the angle is, then take that fraction of 2π. Watch 60° become radians, and the arc it cuts on a circle of radius 2. The picture draws each step on the circle: first the slice of a full turn the arm covers, then the same turn in radians, and last the arc the arm sweeps along the edge.

Try it now

Then set the angle in degrees to 180: the slice is half the circle, and half a turn is π radians. Set the radius to 1 and the arc comes out equal to the angle in radians: each radian sweeps one radius of arc.

Symbols and formula. The two conversions, and the arc:

radians=degrees×π180degrees=radians×180πs=rθ\text{radians} = \text{degrees} \times \frac{\pi}{180} \qquad \text{degrees} = \text{radians} \times \frac{180}{\pi} \qquad s = r\theta

In plain words: multiply by π/180 to go to radians, by 180/π to come back. An arc is the radius times the angle in radians.

Common angles are worth knowing by heart: 90° is π/2 ≈ 1.571, 45° is π/4 ≈ 0.785, 30° is π/6 ≈ 0.524, and 360° is 2π ≈ 6.283. The Greek letter θ ("theta") is the usual name for an angle.

Quick check
What is 90° in radians?
  1. 90π
  2. π, about 3.142
  3. 1/4
  4. π/2, about 1.571
Show the answer

π/2, about 1.571

90° is a quarter turn, and a quarter of 2π is π/2 ≈ 1.571.

Quick check
About how many degrees is 2 radians?
  1. About 180°
  2. 2°
  3. About 360°
  4. About 115°
Show the answer

About 115°

2 × 180/π ≈ 2 × 57.3 ≈ 114.6°: a bit more than a quarter turn and a bit.

Why bother with radians? Degrees are a human choice: 360 is handy because it divides evenly by 2, 3, 4, 5, 6, 8, 9, 10 and 12. Radians come from the circle itself, so formulas built on them stay simple. The arc is just s = rθ, with no stray 180 or π in it. The same is true of the formulas for sine, cosine and their rates of change that calculus and every graphics and physics library rely on, which is why code uses radians everywhere.

Negative angles and more than a turn. A negative angle turns the other way (clockwise), and an angle past 360° or 2π just keeps going around. 450° lands in the same direction as 90°, one full turn later. So does −270°, a three-quarter turn the other way. Angles that land in the same direction give the same sine and cosine.

In your own words
In your own words: what is a radian, and why is a full turn 2π of them?

Write a sentence or two, then compare it with a good answer in the lesson.

In Python: code thinks in radians

Purpose. Python's math functions measure angles in radians, so converting is part of using them.

import math

print(math.pi)
print(math.radians(180), math.radians(90))
print(math.degrees(math.pi / 4), math.degrees(1))
It runs right here in your browser, with nothing to install.

math.pi is π. math.radians turns degrees into radians and math.degrees turns radians back. Under the hood they're the formulas above, × π/180 and × 180/π.

Here is the flow's route written out as a function you can step through: degrees to a fraction of a turn, then to radians, then the arc on a circle of radius 2. Press Next until you're inside to_radians, and watch turn and rad take the same values as the cells in the flow.

A named mistake: degrees where radians are expected. math.sin and math.cos (next lesson) take radians. Hand them a number of degrees and they quietly treat it as radians, so the answer is wrong with no error:

import math

print(math.sin(90), math.sin(math.radians(90)))

sin of a quarter turn is exactly 1, but math.sin(90) treats 90 as 90 radians, more than 14 full turns, and gives about 0.894. Whenever an angle comes from people, convert it with math.radians before it reaches a math function.

Worked example

Worked example: a converter that names its units

Write a converter that takes an angle and its unit, and always returns radians, so a caller can't mix them up.

import math

def to_radians(angle, unit):
    if unit == "degrees":
        return angle * math.pi / 180
    if unit == "radians":
        return angle
    return None

print(to_radians(360, "degrees"), to_radians(1.5, "radians"))
print(to_radians(90, "deg"))
In the lesson you can change this and run it.

Making the caller say which unit they mean turns a silent mistake into a visible one. 360 degrees comes back as 2π ≈ 6.283, and 1.5 radians passes through unchanged. An unknown unit, like "deg", returns None instead of a wrong number, so the problem shows up at once. Many real libraries take the unit as an argument for exactly this reason.

Quick check
What does this print?
import math

print(round(math.cos(math.radians(60)), 4), round(math.cos(60), 4))
  1. 60 60
  2. -0.9524 0.5
  3. 0.5 -0.9524
  4. 0.5 0.5
Show the answer

0.5 -0.9524

cos of 60° is 0.5. But math.cos(60) treats 60 as radians, giving about −0.9524: the named mistake.

Quick check
Which line turns 30 degrees into radians?
  1. math.radians(30)
  2. math.degrees(30)
  3. 30 * 180 / math.pi
  4. 30 / 360
Show the answer

math.radians(30)

math.radians converts degrees to radians: 30 × π/180 ≈ 0.524.

Drill

Convert both ways

Fix the two functions so deg_to_rad(d) gives radians and rad_to_deg(r) gives degrees, then set quarter to a quarter turn in radians.

import math

def deg_to_rad(d):
    return d * 180 / math.pi

def rad_to_deg(r):
    return r * math.pi / 180

quarter = deg_to_rad(90)
print(quarter, rad_to_deg(math.pi))
In the lesson, your code is checked as you write it.
In your own words
Why is passing degrees to math.sin such a common bug?

Write a sentence or two, then compare it with a good answer in the lesson.

In AI and ML: the angle between two arrows

Purpose. A list of numbers can be drawn as an arrow from the origin. Machine learning often asks how close two such arrows are in direction, ignoring their lengths. The angle between them answers that.

Three angles mark the scale:

  • 0°: they point the same way. Similar.
  • 90°: they're at right angles. Unrelated.
  • 180°: they point opposite ways. Opposites.
θ=0∘  sameθ=90∘  unrelatedθ=180∘  opposite\theta = 0^\circ \;\text{same} \qquad \theta = 90^\circ \;\text{unrelated} \qquad \theta = 180^\circ \;\text{opposite}

In plain words: the smaller the angle between two arrows, the more alike they are.

Lesson 51 computes this angle from the numbers themselves, with the cosine you'll meet next lesson. For now, the picture is the point: word meanings, images and documents become arrows, and similar ones point nearly the same way.

Quick check
Two arrows: one points right, (1, 0), and one points up, (0, 1). What's the angle between them, and what does it mean?
  1. 180°: opposite
  2. 90°: unrelated
  3. 0°: the same
  4. 45°: half alike
Show the answer

90°: unrelated

Right and up are a quarter turn apart: 90°, the angle ML reads as "unrelated".

Why direction and not length? Two documents about tents, one short and one long, have word counts that point the same way, even though the long one's numbers are all bigger. Comparing directions treats them as alike, which is what we want. In Python, the angle in radians from lesson 51 will come straight out of math.acos; converting it with math.degrees makes it readable. Say a model measured the angles between three pairs of arrows as π/6, π/2 and 5π/6 radians:

import math

for rad in [math.pi / 6, math.pi / 2, 5 * math.pi / 6]:
    print(round(math.degrees(rad)))

The picture draws the three pairs. Arrow a stays put; press Next to swing arrow b from 30° to 90° to 150°.

In the real tools. PyTorch, the library most models are built with, measures angles in radians as well, and converts a whole list of them in one line:

Quick check
What does this print?
import math

print(round(math.degrees(math.pi / 3)), round(math.radians(180), 2))
  1. 60 180
  2. 3.14 60
  3. 60 3.14
  4. 1 180
Show the answer

60 3.14

π/3 radians is a sixth of a turn, 60°. 180° is π radians, about 3.14.

Drill

Label pairs of arrows

Angles between three pairs of arrows are given in radians. Convert each to degrees, rounded to a whole number, in a, b and c. Then set most_alike to the letter of the pair that points most nearly the same way.

import math

a = 0.1
b = 1.5708
c = 3.0
most_alike = "c"
print(a, b, c, most_alike)
In the lesson, your code is checked as you write it.
In your own words
What would an angle of 175° between two word arrows suggest about the words?

Write a sentence or two, then compare it with a good answer in the lesson.

Goes deeper in

Practice what you just read

  • 4 code examples you can edit and run
  • a practice exercise that checks your code
  • a 5-question quiz
  • 9 review cards for spaced repetition

Try a quiz question

What is 135° in radians?

  1. 3π/4
  2. π/4
  3. 135π
  4. 3/4

Answer it at the end of the lesson to see if you're right, and why.

Before this lesson

Keep learning

Where this lesson leads.

575 lessons in thirteen phases. 176 are free without an account, and a free account opens the rest. See every lesson.

Foundation · about 96 hours of study

Foundation math

From whole numbers to the math inside a neural network: each idea by hand, in Python, and in AI 118 lessons All free
  1. Numbers and place value FreeWhat a digit's place is worth, the number line, and Python as a calculator that never tires.36 min
  2. Multiplying and dividing: groups FreeEqual groups, quotient and remainder, and cutting training data into batches.35 min
  3. Order of operations, and names for numbers FreeBrackets, powers, then multiply and divide, then add and subtract; variables hold numbers.36 min
  4. Numbers below zero FreeThe number line through zero, sign rules, distance from zero, and an error's direction and size.37 min
  5. Fractions: equal parts, equal fractions, adding FreePieces of a whole, equal fractions, and re-cutting to add; accuracy as a fraction.45 min
  6. Multiplying and dividing fractions FreeA share of a share, dividing by flipping, and why chances in a row get small.35 min
  7. Decimals and rounding FreeFractions in place value, rounding, and why 0.1 + 0.2 isn't exactly 0.3.36 min
  8. Percentages FreePer hundred, percent change, percentage points, and the accuracy and error rates of models.35 min
  9. Ratios, rates and proportion FreeSharing in a ratio, rates per unit, scaling, and splitting data 80/10/10.35 min
  10. Powers and roots FreeRepeated multiplying, the laws of exponents, square roots, and squared error.43 min
  11. Very big and very small numbers FreePowers of ten, e-notation like 3e-4, orders of magnitude, and a model's size in memory.36 min
  12. Bits, bytes and floats: how numbers are stored FreeBase 2, what n bits can hold, a float as sign, power and digits, and a tensor's memory.35 min
  13. Review: find the slip (numbers) FreeBroken calculations to fix, mixed practice from the whole module, and its formula sheet.34 min
  14. Letters for numbers FreeVariables, terms and like terms, substitution, and a model's formula as a Python function.41 min
  15. Expanding and factoring FreeBrackets as areas, pulling out common factors, and a squared error expanded into a bowl.41 min
  16. Solving equations: keep the balance FreeThe same move on both sides, undoing steps in reverse, and running a model's formula backward.41 min
  17. Rearranging a formula FreeMaking any letter the subject, round-trip checks, and planning a training run.36 min
  18. Inequalities and true-or-false FreeRanges, flipping the sign, if and elif, and the thresholds, clips and ReLU inside a model.42 min
  19. Functions: a rule from input to output Freef(x) notation, tables and graphs, domain and range, loops over lists, and loss as a function.42 min
  20. Chaining and undoing functions Freeg(f(x)), inverses that undo, scaling and unscaling, and a network as a chain.42 min
  21. Straight lines: slope and intercept FreeRise over run, the line through two points, and a model's weight and bias as slope and intercept.42 min
  22. Two equations, two unknowns FreeSubstitution and elimination, where lines cross, and why models are fitted, not solved.42 min
  23. Quadratics: bowls and their lowest point FreeRoots by factoring and by formula, the discriminant, the vertex, and the best weight of a model.42 min
  24. Exponentials: growth and decay FreeThe same factor each step, the number e, and decaying learning rates.43 min
  25. Logarithms: the power question FreeTo what power?, the laws of logs, and adding log-probabilities instead of multiplying.45 min
  26. Sequences and Σ FreeArithmetic and geometric sequences, Σ as a loop that adds, and mean squared error.40 min
  27. Weighted and moving averages FreeWeights that add to 1, a window average, the exponential moving average, and smoothing a loss curve.35 min
  28. Sets, and reading the symbols FreeSets, union and intersection, ℝⁿ and f : ℝⁿ → ℝᵐ, and reading a paper's first equation.41 min
  29. Review: find the slip (algebra) FreeBroken algebra and code to fix, mixed practice from the whole module, and its formula sheet.34 min
  30. Transposing step by step: undo in reverse order FreeA formula's layers, the opposite of each, peeling from the outside in, conditions, and round-trip checks.35 min
  31. Formulas with fractions: clear them first FreeClearing denominators, cross-multiplying, a letter in the bottom, and reciprocal formulas like 1/R = 1/R₁ + 1/R₂.35 min
  32. When the letter appears twice: collect and factor FreeGathering the letter on one side, factoring it out, dividing by the bracket, and rearranging precision and F1.35 min
  33. Squares, roots and powers FreeSquare roots with ±, squaring to undo a root, cube and nth roots, and the √d inside attention.40 min
  34. When the letter is squared and plain: quadratics FreeRearranging into ax² + bx + c = 0, the formula, completing the square, and choosing the root that fits.35 min
  35. Letters in the power: exponentials and logarithms FreeTaking logs to bring a power down, exponentiating to free a letter, and the logit that undoes the sigmoid.40 min
  36. Rearranging inequalities: when the sign flips FreeThe four moves on an inequality, negatives and reciprocals that flip it, logs below 1, and sample sizes.35 min
  37. Inverse functions, lines and scaling FreeUndoing a function by making x the subject, domains that allow it, line forms, and unscaling predictions.40 min
  38. Sequences and sums: find n, a, d and r FreeEvery letter of the arithmetic and geometric formulas as the subject, and an average's window from its decay.40 min
  39. Combining formulas: substitute and eliminate FreePutting one formula inside another to remove a letter, and sizing a training run from a time or money budget.35 min
  40. Review: rearrange anything (algebra) FreeBroken rearrangements to fix, mixed practice from the whole algebra block, a strategy chart, and its formula sheet.35 min
  41. Coordinates and distance FreePoints as (x, y), Pythagoras, distance in any number of coordinates, and nearest neighbors.42 min
  42. Angles, degrees and radians FreeMeasuring a turn, converting units, arcs, and the angle between two arrows.36 min
  43. Sine and cosine FreeAcross and up: right triangles, the unit circle, and directions and rotations.42 min
  44. Waves: height, speed and shift FreeAmplitude, period and phase, sampling a wave, and position codes in transformers.37 min
  45. Review: find the slip (shapes and waves) FreeBroken geometry and code to fix, mixed practice from the module, and its formula sheet.29 min
  46. Angles, triangles and waves: rearranging with sin, cos and tan FreeSides and angles from SOH CAH TOA, principal values, arcs, polar coordinates, and a wave's time and period.45 min
  47. Vectors: lists of numbers that point FreeA list, a point and an arrow; components, dimension, NumPy arrays, and data as vectors.42 min
  48. Adding and scaling vectors FreeComponent-wise sums, scalar multiples, mixes, and the weight update w − ηg.43 min
  49. Length and distance: norms FreeL2, L1 and max norms, unit vectors, distance, and the norms inside losses and clipping.42 min
  50. The dot product FreeMultiply in pairs and add; a·a as squared length; a @ b; one neuron as a dot product.43 min
  51. Angle, cosine similarity and projection FreeDirection without length, perpendicular vectors, shadows, and search by meaning.45 min
  52. Perpendicular directions: bases and coordinates FreeOrthonormal directions, coordinates as dot products, rebuilding a vector, and taking a direction out.35 min
  53. Matrices: tables of numbers FreeRows, columns and entries; two-dimensional arrays and slices; a data set as a matrix.41 min
  54. Adding, scaling and transposing matrices FreeEntry-by-entry sums and scalings, the transpose, mean images, and tables turned around.36 min
  55. A matrix times a vector FreeEach row dotted with the vector, the size rule, A @ x, and a layer acting on one example.42 min
  56. Matrix multiplication FreeRow meets column, the size rule, order matters, and a batch through a layer: X W + b.45 min
  57. Identity, diagonal, triangular and symmetric FreeFour patterns and their jobs: rescaling, distance tables, and the causal mask.37 min
  58. Matrices as movements of space FreeStretches, flips, shears and rotations; columns as landing spots; chaining; a layer moving data.42 min
  59. Determinant and inverse FreeThe area factor ad − bc, singular matrices, undoing a matrix, and redundant features.42 min
  60. Solving systems by elimination FreeAugmented matrices, row moves, back-substitution, the three outcomes, and fitting weights.45 min
  61. Independence, span and rank FreeRedundant vectors, span, rank, outer products, and low-rank updates like LoRA.42 min
  62. Eigenvectors: directions that only stretch FreeAv = λv, checking candidates, np.linalg.eig, and the main direction of a data cloud.41 min
  63. SVD and PCA: the important directions first FreeA matrix as pieces by size, the best rank-k copy, compression, and PCA maps of data.45 min
  64. Tensors, shapes and broadcasting FreeAxes and shapes, reshape, axis=, broadcasting, and shapes through a small model.43 min
  65. One-hot vectors and lookup tables: embeddings FreeA one-hot row picks a table's row, a sentence looked up as vectors, and a score for every word.35 min
  66. Sliding dot products: convolution FreeA small pattern slid along a list and over a grid, output sizes, stride and padding, and shared weights.40 min
  67. Review: find the slip (vectors and matrices) FreeShape slips to fix, mixed practice from the module, and its formula sheet with shapes.36 min
  68. Vector equations: rearranging with arrows FreeSolving for a vector or a scale, recovering a gradient from two weight snapshots, and an angle from a dot product.40 min
  69. Matrix equations: multiply by the inverse, on the correct side FreeNo dividing by a matrix: inverses from the left or right, order, transposes, and the normal equations.40 min
  70. Rates of change FreeChange over change, secants, rates from readings with np.diff, and reading a loss curve.41 min
  71. Limits: what a value heads toward FreeApproaching from both sides, holes, corners and jumps, epsilon, and judging activations.37 min
  72. The derivative: slope at a point FreeShrinking secants, f′(x) and dy/dx, Δy ≈ f′Δx, and which way a weight should move.45 min
  73. Derivative rules FreeConstants, powers, multiples, sums, eˣ and ln x, checked numerically, and a squared error's slope.41 min
  74. The product rule and the chain rule FreeProducts and chains of functions, forward then backward, and one neuron's dL/dw.45 min
  75. Lowest points and curvature Freef′ = 0, the second-derivative test, tables, local and global minima, and convex losses.43 min
  76. Standing in for a curve near a point FreeTangent lines, a curvature term, growing error, and why learning rates must be small.37 min
  77. Partial derivatives FreeOne input at a time, ∂, nudging in Python, and the two slopes of a line's loss.41 min
  78. The gradient FreeAll the slopes as a vector, steepest climb and descent, a numerical gradient, and the loss gradient.42 min
  79. Gradient descent FreeStepping against the gradient, the learning rate, a training loop, and fitting a line.45 min
  80. Faster descent: momentum and Adam FreeMomentum and Adam by hand, the bias correction, and three optimizers down one narrow valley.40 min
  81. The chain rule with many paths: backpropagation by hand FreeGraphs, multiply along paths and add across them, gradient checks, and a 2-2-1 network by hand.45 min
  82. Automatic differentiation: how PyTorch finds every slope FreeA tape of steps walked backward, and requires_grad, backward(), .grad, zero_grad() and no_grad().40 min
  83. Jacobians and Hessians FreeSlopes of vector functions, a layer's Jacobian, second partials, and bowls, domes and saddles.42 min
  84. Integrals: adding up thin slices FreeStrip and trapezoid sums, summing undoes differencing, probability as area, and AUC.43 min
  85. Review: find the slip (calculus) FreeCalculus slips to fix, mixed practice from the module, and its formula sheet.36 min
  86. Rearranging in calculus: slopes, steps and constants FreeSetting a slope to zero, Newton's step, the chain rule turned around, constants from a point, and learning rates.45 min
  87. Counting: choices, orders and groups FreeThe counting principle, factorials, ordered picks and groups, and why attention's cost grows with the square of the length.43 min
  88. Probability: from counts to chances FreeEqually likely outcomes, the complement, distributions, seeded simulation, and a next-word model.43 min
  89. Combining events: and, or, independent FreeThe or rule, independence, probability trees, drawing with and without replacement, and chains of steps.42 min
  90. Conditional probability and Bayes' rule FreeConditionals from tables, why P(A | B) isn't P(B | A), Bayes' rule, and precision and recall.45 min
  91. Random variables and distributions FreeUncertain numbers, the probability of a range, sampling by slices, and sampling versus argmax.42 min
  92. Expected value, variance and standard deviation FreeProbability-weighted averages, spread in the data's own units, and a training loss as an expected value.42 min
  93. Bernoulli, binomial, uniform and normal FreeYes-or-no trials, counts of yeses, the 68-95-99.7 rule, z-scores, and an accuracy's error bar.45 min
  94. Two variables at once: covariance and correlation FreeJoint tables and marginals, covariance, correlation, the covariance matrix, and features that carry the same information.45 min
  95. Review: find the slip (probability) FreeProbability slips to fix, mixed practice from the module, and its formula sheet.36 min
  96. Probability formulas: solve for the missing chance FreeConditionals, Bayes' rule for the prior, the or rule, expected values, variance, and z-scores turned around.45 min
  97. Describing data: center, spread and scale FreeMean, median and mode, variance and standard deviation, percentiles, outliers, and standardizing features.42 min
  98. Samples, the law of large numbers and the central limit theorem FreeSamples and populations, the standard error σ/√n, the bell of averages, and error bars on test scores.43 min
  99. Is the difference real? Comparing two models FreePaired differences, a bootstrap interval, what a p-value is and isn't, and why many tries make lucky wins.40 min
  100. Maximum likelihood FreeLikelihoods as products, log-likelihoods as sums, grid search, underflow, and the negative log-likelihood loss.45 min
  101. Linear regression: the best line FreeResiduals, least squares by formula, three roads to one line, the matrix form, and train versus test error.45 min
  102. Logistic regression: a line that answers yes or no FreeThe sigmoid, the log loss, its slope p − y, a training loop, and choosing a threshold.45 min
  103. Scoring a classifier: confusion table, precision, recall, F1 FreeThe four cells, accuracy, precision, recall and F1, and what moving a threshold does to each.35 min
  104. Softmax: scores into probabilities FreeExponentiate and share out, shifting and temperature, the safe softmax, and a classifier's last step.43 min
  105. Surprise, entropy and cross-entropy FreeSurprise in bits, entropy, cross-entropy and KL divergence, perplexity, and a language model's loss.45 min
  106. KL divergence: how far one distribution is from another FreeKL by hand, cross-entropy as entropy plus KL, why it isn't symmetric, and a soft-target loss.35 min
  107. Review: find the slip (statistics and information) FreeStatistics slips to fix, mixed practice from the module, and its formula sheet.38 min
  108. Statistics and information: n, z, logits and bits FreeSample sizes from error bars, inputs from probabilities, logit gaps from softmax, and chances from bits and losses.40 min
  109. One neuron, start to finish FreeWeighted sum, activation, loss, slopes and update, by hand and in code, and what one straight line can and can't split.45 min
  110. A layer and a small network as matrices FreeTwo layers on a batch, the shape of every matrix, adding a hidden unit, and XOR solved.45 min
  111. Training a small network FreeThe backward pass in matrix form, gradient checks, a full training loop, and reading loss curves.45 min
  112. The same network in PyTorch Freenn.Sequential with the NumPy weights loaded, the same loss and slopes, then SGD and mini-batches.45 min
  113. Attention as matrix math FreeScaled dot-product scores, the causal mask, a row-by-row softmax, and blending value vectors.45 min
  114. Residual connections and layer norm FreeAdding the input back and why its slope keeps learning alive, layer norm by hand, and add and norm.40 min
  115. A transformer block, start to finish FreeA sentence through embeddings, attention, add and norm, a small network and next-word scores, every shape named.45 min
  116. Planning a model: rearranging the formulas of a working network FreeLayer widths from parameter counts, sizes from memory and compute, the attention scale, and a training plan.40 min
  117. Final test: transpose any formula FreeSlips to fix from every topic, mixed practice of every kind of rearranging, the strategy chart and the full sheet.45 min
  118. Capstone: a sign reader from the formulas FreeBuild, train and test a trail-sign classifier with NumPy alone, and report its accuracy with an error bar.45 min
Part of a free course 118 lessons

The Foundation Math For Ai & ML: from arithmetic to attention

Learn the math behind AI from arithmetic up: numbers, algebra, vectors and matrices, calculus, probability and statistics, each shown as numbers moving and checked in Python, ending with a network you build and train from the formulas.

Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write